Vote and KNN outlier detection in Wireless Sensor Networks
Aymen Abid, Salim El Khediri, Tarek Moulahi, Rym Chéour, Abdennaceur Kachouri · 2021
The target of a Wireless Sensor Network (WSN) designer is to improve the robustness of the network while taking into account constraints such as verifying the detection of anomalies. Preventing anomalies can be assured by data analysis via outliers identification as it strongly affects decision-making in the case of smart-home, e-health and other high-risk applications. In this paper, we study some families of outliers and we propose to detect data anomalies using K Nearest Neighbours (KNN) and Voting techniques by a benchmark suitable to be a simulation for a smart-house. In order to evaluate the dependability, some performance metrics are analyzed such as data rate detection, precision, specificity and accuracy. Performance results are in the order of 100% detection rate with reduced false alarm and fast response time compared to some other existing ones.